vllm-project/vllm

[Feature]: Integrate fused `kMoEFinalizeARResidualRMSNorm` from FlashInfer

開放

#40,544 建立於 2026年4月21日

 (5 則留言) (1 個反應) (0 位負責人)Python (16,816 個分叉)batch import
feature requesthelp wanted

倉庫指標

星標
 (80,034 顆星)
PR 合併指標
 (平均合併 3天 17小時) (30 天內合併 993 個 PR)

描述

🚀 The feature, motivation and pitch

Available today via FlashInfer 0.6.8, we can leverage this fused MoE Finalize + ResidualAdd + AllReduce + RMSNorm https://github.com/flashinfer-ai/flashinfer/pull/2982.

This should be added as a new torch.compile custom pass. I think moe_finalize might still be inside the wrapped fused_moe op so this might require pulling that out.

Alternatives

No response

Additional context

No response

Before submitting a new issue...

  • Make sure you already searched for relevant issues, and asked the chatbot living at the bottom right corner of the documentation page, which can answer lots of frequently asked questions.

貢獻者指南